基于贝叶斯结构的.docVIP

基于贝叶斯网络的老年重症患者的预后评估 曾安1 李晓兵1 潘丹2 广东工业大学计算机学院，广州，510006; 2.美国Batteries Plus公司, 哈特兰市，威斯康辛州 53029） 摘 要：在重症患者中，老年人占有较大比例占用ICU)资源但治疗预后却不明确因此，研究老年人在ICU中的简化问题，贝叶斯网络随机变量之间的非线性），模型结果易于理解高龄患者中受益ICU资源的配置An Evaluation Model of the Prognosis for Elderly Critical Patients Based on Bayesian Network Zeng An1, Li Xiaobing1, PAN Dan2 Computer institute of Guangdong university of technology, Guangdong, 510006; Batteries Plus LLC., Hartland, Wisconsin, U.S.A, 53029) Abstract: In critically ill patients, the elderly account for a large proportion and take up more ICU resources, but the treatment effect and prognosis are not clear. Therefore, prognosis research for elderly critical patients is important. At present, most research focuses on the prognostic factors by using the regression analysis which often assumes a linear relationship between death and various risk factors for the sake of simplifying problems. The Bayesian networks are an effective tool for uncertain reasoning and nonlinear analysis, and the generated model results are comprehensible. In this paper, an evaluation model of the prognosis for elderly critical patients based on Bayesian network was constructed. Firstly, a Bayesian approach based on Minimum Description Length (MDL) and K2 algorithm was proposed to obtain the optimal network structure, and then the maximum likelihood method is used for estimation parameter learning. At last, Bayesian inference is employed to get the final prediction results. Four-fold cross sampling results show that the prediction accuracy of the model presented in this paper is superior to conventional BP neural networkand K2 algorithm based on Bayesian learning method And the prediction accuracy has been improved by 6.43% and 27.2%, It is helpful for the doctors to calculate the degree of elderly patients benifited from ICU cure and to estimate the allocation of ICU resoures. Key words: Bayesian networks; estimation parameter learning; evaluation of the